Constructive Universal High-Dimensional Distribution Generation through Deep ReLU Networks

• URL: http://arxiv.org/abs/2006.16664v2
• Date: Sat, 5 Jun 2021 20:23:27 GMT
• Title: Constructive Universal High-Dimensional Distribution Generation through Deep ReLU Networks
• Authors: Dmytro Perekrestenko, Stephan M\"uller, Helmut B\"olcskei
• Abstract summary: We present an explicit deep neural network construction that transforms uniformly distributed one-dimensional noise into an arbitrarily close approximation of any two-dimensional Lipschitz-continuous target distribution. We elicit the importance of depth - in our neural network construction - in driving the Wasserstein distance between the target distribution and the approximation realized by the network to zero.
• Score: 3.4591414173342647
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We present an explicit deep neural network construction that transforms uniformly distributed one-dimensional noise into an arbitrarily close approximation of any two-dimensional Lipschitz-continuous target distribution. The key ingredient of our design is a generalization of the "space-filling" property of sawtooth functions discovered in (Bailey & Telgarsky, 2018). We elicit the importance of depth - in our neural network construction - in driving the Wasserstein distance between the target distribution and the approximation realized by the network to zero. An extension to output distributions of arbitrary dimension is outlined. Finally, we show that the proposed construction does not incur a cost - in terms of error measured in Wasserstein-distance - relative to generating $d$-dimensional target distributions from $d$ independent random variables.

Related papers

• Learning with Norm Constrained, Over-parameterized, Two-layer Neural Networks [54.177130905659155]
  Recent studies show that a reproducing kernel Hilbert space (RKHS) is not a suitable space to model functions by neural networks. In this paper, we study a suitable function space for over- parameterized two-layer neural networks with bounded norms.
  arXiv  Detail & Related papers  (2024-04-29T15:04:07Z)
• Quantitative CLTs in Deep Neural Networks [12.845031126178593]
  We study the distribution of a fully connected neural network with random Gaussian weights and biases. We obtain quantitative bounds on normal approximations valid at large but finite $n$ and any fixed network depth. Our bounds are strictly stronger in terms of their dependence on network width than any previously available in the literature.
  arXiv  Detail & Related papers  (2023-07-12T11:35:37Z)
• On the Effective Number of Linear Regions in Shallow Univariate ReLU Networks: Convergence Guarantees and Implicit Bias [50.84569563188485]
  We show that gradient flow converges in direction when labels are determined by the sign of a target network with $r$ neurons. Our result may already hold for mild over- parameterization, where the width is $tildemathcalO(r)$ and independent of the sample size.
  arXiv  Detail & Related papers  (2022-05-18T16:57:10Z)
• Quantitative Gaussian Approximation of Randomly Initialized Deep Neural Networks [1.0878040851638]
  We show how the hidden and output layers sizes affect the Gaussian behaviour of the network. Our explicit inequalities indicate how the hidden and output layers sizes affect the Gaussian behaviour of the network.
  arXiv  Detail & Related papers  (2022-03-14T14:20:19Z)
• Robust Estimation for Nonparametric Families via Generative Adversarial Networks [92.64483100338724]
  We provide a framework for designing Generative Adversarial Networks (GANs) to solve high dimensional robust statistics problems. Our work extend these to robust mean estimation, second moment estimation, and robust linear regression. In terms of techniques, our proposed GAN losses can be viewed as a smoothed and generalized Kolmogorov-Smirnov distance.
  arXiv  Detail & Related papers  (2022-02-02T20:11:33Z)
• High-Dimensional Distribution Generation Through Deep Neural Networks [2.141079906482723]
  We show that every $d$-dimensional probability distribution of bounded support can be generated through deep ReLU networks. We find that, for histogram target distributions, the number of bits needed to encode the corresponding generative network equals the fundamental limit for encoding probability distributions.
  arXiv  Detail & Related papers  (2021-07-26T20:35:52Z)
• Point Cloud Upsampling via Disentangled Refinement [86.3641957163818]
  Point clouds produced by 3D scanning are often sparse, non-uniform, and noisy. Recent upsampling approaches aim to generate a dense point set, while achieving both distribution uniformity and proximity-to-surface. We formulate two cascaded sub-networks, a dense generator and a spatial refiner.
  arXiv  Detail & Related papers  (2021-06-09T02:58:42Z)
• Distributional Sliced Embedding Discrepancy for Incomparable Distributions [22.615156512223766]
  Gromov-Wasserstein (GW) distance is a key tool for manifold learning and cross-domain learning. We propose a novel approach for comparing two computation distributions, that hinges on the idea of distributional slicing, embeddings, and on computing the closed-form Wasserstein distance between the sliced distributions.
  arXiv  Detail & Related papers  (2021-06-04T15:11:30Z)
• On the capacity of deep generative networks for approximating distributions [8.798333793391544]
  We prove that neural networks can transform a one-dimensional source distribution to a distribution arbitrarily close to a high-dimensional target distribution in Wasserstein distances. It is shown that the approximation error grows at most linearly on the ambient dimension. $f$-divergences are less adequate than Waserstein distances as metrics of distributions for generating samples.
  arXiv  Detail & Related papers  (2021-01-29T01:45:02Z)
• From deep to Shallow: Equivalent Forms of Deep Networks in Reproducing Kernel Krein Space and Indefinite Support Vector Machines [63.011641517977644]
  We take a deep network and convert it to an equivalent (indefinite) kernel machine. We then investigate the implications of this transformation for capacity control and uniform convergence. Finally, we analyse the sparsity properties of the flat representation, showing that the flat weights are (effectively) Lp-"norm" regularised with 0p1.
  arXiv  Detail & Related papers  (2020-07-15T03:21:35Z)
• Variational Hyper-Encoding Networks [62.74164588885455]
  We propose a framework called HyperVAE for encoding distributions of neural network parameters theta. We predict the posterior distribution of the latent code, then use a matrix-network decoder to generate a posterior distribution q(theta)
  arXiv  Detail & Related papers  (2020-05-18T06:46:09Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.